EUVIMEDΑνακαλύψτε το EUVIMED
Crossref

A Physics‐Guided Residual Neural Network for Small‐Sample Cross‐Material‐Source Prediction of Contact Fatigue Life in Plastic Gears

Shuiyu Liu, Baofeng He, Edward Wang, Zhaoyao Shi

Fatigue & Fracture of Engineering Materials & Structures · 2026-11-19

DOI: 10.1111/ffe.70538 ↗

At a glance

Journal article in Fatigue & Fracture of Engineering Materials & Structures, published online on 2026-11-19. Written by Shuiyu Liu and 3 co-authors. 39 references. Funded by: Natural Science Foundation of Chongqing.

ΠερίληψηΒιβλιογραφικά στοιχείαCiteRelated studies

Abstract (original language)

In this study, a physics‐guided residual neural network (PGRNN) was developed for small‐sample cross‐material‐source prediction of plastic gear contact fatigue life and evaluated using POM, PEEK, and PA66 literature datasets. Stress and temperature were normalized by material strength, stiffness, and characteristic temperatures to describe comparable mechanical and thermal states across polymers. A Basquin‐based physical backbone represented the main fatigue trend, while a residual network captured nonlinear thermo‐mechanical coupling. Leave‐one‐material‐out (LOMO) validation held out each material and its single, distinct literature source together; repeated within‐material validation was also performed. PGRNN achieved the lowest root‐mean‐square error in all three LOMO folds compared with artificial neural network, support vector regression, and random forest baselines, with most predictions within the factor‐of‐three error band. Ablation and contribution analyses further showed that the physical backbone dominated the response, whereas bounded residual corrections improved accuracy without reversing the expected degradation trends with increasing stress and temperature.

Funding

  • Natural Science Foundation of Chongqing

Cite

APA

Liu, S., He, B., Wang, E., & Shi, Z. (2026). A Physics‐Guided Residual Neural Network for Small‐Sample Cross‐Material‐Source Prediction of Contact Fatigue Life in Plastic Gears. Fatigue & Fracture of Engineering Materials & Structures. https://doi.org/10.1111/ffe.70538

Vancouver

Liu S, He B, Wang E, Shi Z. A Physics‐Guided Residual Neural Network for Small‐Sample Cross‐Material‐Source Prediction of Contact Fatigue Life in Plastic Gears. Fatigue & Fracture of Engineering Materials & Structures. 2026. doi:10.1111/ffe.70538

BibTeX
@article{Liu2026,
  author = {Liu, Shuiyu and He, Baofeng and Wang, Edward and Shi, Zhaoyao},
  title = {A Physics‐Guided Residual Neural Network for Small‐Sample Cross‐Material‐Source Prediction of Contact Fatigue Life in Plastic Gears},
  journal = {Fatigue & Fracture of Engineering Materials & Structures},
  year = {2026},
  doi = {10.1111/ffe.70538}
}
Start for free →